| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03251239535072747, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 6.1699113845825195, | |
| "eval_runtime": 107.4792, | |
| "eval_samples_per_second": 24.107, | |
| "eval_steps_per_second": 12.058, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 4.72934627532959, | |
| "learning_rate": 0.0002, | |
| "loss": 4.9735, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 6.465259075164795, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5147, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 3.9124128818511963, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1793, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006502479070145493, | |
| "grad_norm": 5.1272406578063965, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0771, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "grad_norm": 8.364299774169922, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7652, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008128098837681867, | |
| "eval_loss": 2.840857982635498, | |
| "eval_runtime": 107.5901, | |
| "eval_samples_per_second": 24.082, | |
| "eval_steps_per_second": 12.046, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00975371860521824, | |
| "grad_norm": 14.7822847366333, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7234, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.011379338372754613, | |
| "grad_norm": 6.248720169067383, | |
| "learning_rate": 0.0002, | |
| "loss": 2.857, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.013004958140290986, | |
| "grad_norm": 8.499987602233887, | |
| "learning_rate": 0.0002, | |
| "loss": 2.538, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.014630577907827359, | |
| "grad_norm": 5.129115581512451, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7305, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.016256197675363734, | |
| "grad_norm": 8.391996383666992, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5496, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.016256197675363734, | |
| "eval_loss": 2.6107428073883057, | |
| "eval_runtime": 107.5036, | |
| "eval_samples_per_second": 24.102, | |
| "eval_steps_per_second": 12.055, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017881817442900107, | |
| "grad_norm": 3.870755910873413, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5469, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.01950743721043648, | |
| "grad_norm": 3.6526923179626465, | |
| "learning_rate": 0.0002, | |
| "loss": 2.589, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.021133056977972853, | |
| "grad_norm": 4.250131607055664, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3978, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.022758676745509226, | |
| "grad_norm": 7.281190872192383, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4315, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0243842965130456, | |
| "grad_norm": 5.660935878753662, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3926, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0243842965130456, | |
| "eval_loss": 2.461916208267212, | |
| "eval_runtime": 107.4978, | |
| "eval_samples_per_second": 24.103, | |
| "eval_steps_per_second": 12.056, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.026009916280581972, | |
| "grad_norm": 5.260167121887207, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4317, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.027635536048118345, | |
| "grad_norm": 4.37868070602417, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4482, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.029261155815654718, | |
| "grad_norm": 5.191292762756348, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2507, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03088677558319109, | |
| "grad_norm": 4.608124732971191, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3221, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03251239535072747, | |
| "grad_norm": 3.7295658588409424, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3791, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03251239535072747, | |
| "eval_loss": 2.360269546508789, | |
| "eval_runtime": 107.5619, | |
| "eval_samples_per_second": 24.088, | |
| "eval_steps_per_second": 12.049, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.639174412992512e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |